1 files changed, 88 insertions, 27 deletions

diff --git a/include/linux/sched.h b/include/linux/sched.h
index 0dd42a02df2e..f712465b05c5 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -107,8 +107,18 @@ extern unsigned long this_cpu_load(void);
 extern void calc_global_load(unsigned long ticks);
 extern void update_cpu_load_nohz(void);
 
+/* Notifier for when a task gets migrated to a new CPU */
+struct task_migration_notifier {
+        struct task_struct *task;
+        int from_cpu;
+        int to_cpu;
+};
+extern void register_task_migration_notifier(struct notifier_block *n);
+
 extern unsigned long get_parent_ip(unsigned long addr);
 
+extern void dump_cpu_task(int cpu);
+
 struct seq_file;
 struct cfs_rq;
 struct task_group;
@@ -434,13 +444,28 @@ struct cpu_itimer {
 };
 
 /**
+ * struct cputime - snaphsot of system and user cputime
+ * @utime: time spent in user mode
+ * @stime: time spent in system mode
+ *
+ * Gathers a generic snapshot of user and system time.
+ */
+struct cputime {
+        cputime_t utime;
+        cputime_t stime;
+};
+
+/**
  * struct task_cputime - collected CPU time counts
  * @utime:              time spent in user mode, in &cputime_t units
  * @stime:              time spent in kernel mode, in &cputime_t units
  * @sum_exec_runtime:   total time spent on the CPU, in nanoseconds
  *
- * This structure groups together three kinds of CPU time that are
- * tracked for threads and thread groups.  Most things considering
+ * This is an extension of struct cputime that includes the total runtime
+ * spent by the task from the scheduler point of view.
+ *
+ * As a result, this structure groups together three kinds of CPU time
+ * that are tracked for threads and thread groups.  Most things considering
  * CPU time want to group these counts together and treat all three
  * of them in parallel.
  */
@@ -581,7 +606,7 @@ struct signal_struct {
         cputime_t gtime;
         cputime_t cgtime;
 #ifndef CONFIG_VIRT_CPU_ACCOUNTING
-        cputime_t prev_utime, prev_stime;
+        struct cputime prev_cputime;
 #endif
         unsigned long nvcsw, nivcsw, cnvcsw, cnivcsw;
         unsigned long min_flt, maj_flt, cmin_flt, cmaj_flt;
@@ -631,9 +656,10 @@ struct signal_struct {
         struct rw_semaphore group_rwsem;
 #endif
 
-        int oom_score_adj;      /* OOM kill score adjustment */
-        int oom_score_adj_min;  /* OOM kill score adjustment minimum value.
-                                 * Only settable by CAP_SYS_RESOURCE. */
+        oom_flags_t oom_flags;
+        short oom_score_adj;            /* OOM kill score adjustment */
+        short oom_score_adj_min;        /* OOM kill score adjustment min value.
+                                         * Only settable by CAP_SYS_RESOURCE. */
 
         struct mutex cred_guard_mutex;  /* guard against foreign influences on
                                          * credential calculations
@@ -1061,6 +1087,7 @@ struct sched_class {
 
 #ifdef CONFIG_SMP
         int  (*select_task_rq)(struct task_struct *p, int sd_flag, int flags);
+        void (*migrate_task_rq)(struct task_struct *p, int next_cpu);
 
         void (*pre_schedule) (struct rq *this_rq, struct task_struct *task);
         void (*post_schedule) (struct rq *this_rq);
@@ -1095,6 +1122,18 @@ struct load_weight {
         unsigned long weight, inv_weight;
 };
 
+struct sched_avg {
+        /*
+         * These sums represent an infinite geometric series and so are bound
+         * above by 1024/(1-y).  Thus we only need a u32 to store them for for all
+         * choices of y < 1-2^(-32)*1024.
+         */
+        u32 runnable_avg_sum, runnable_avg_period;
+        u64 last_runnable_update;
+        s64 decay_count;
+        unsigned long load_avg_contrib;
+};
+
 #ifdef CONFIG_SCHEDSTATS
 struct sched_statistics {
         u64                     wait_start;
@@ -1155,6 +1194,15 @@ struct sched_entity {
         /* rq "owned" by this entity/group: */
         struct cfs_rq           *my_q;
 #endif
+/*
+ * Load-tracking only depends on SMP, FAIR_GROUP_SCHED dependency below may be
+ * removed when useful for applications beyond shares distribution (e.g.
+ * load-balance).
+ */
+#if defined(CONFIG_SMP) && defined(CONFIG_FAIR_GROUP_SCHED)
+        /* Per-entity load-tracking */
+        struct sched_avg        avg;
+#endif
 };
 
 struct sched_rt_entity {
@@ -1318,7 +1366,7 @@ struct task_struct {
         cputime_t utime, stime, utimescaled, stimescaled;
         cputime_t gtime;
 #ifndef CONFIG_VIRT_CPU_ACCOUNTING
-        cputime_t prev_utime, prev_stime;
+        struct cputime prev_cputime;
 #endif
         unsigned long nvcsw, nivcsw; /* context switch counts */
         struct timespec start_time;             /* monotonic time */
@@ -1479,6 +1527,14 @@ struct task_struct {
         short il_next;
         short pref_node_fork;
 #endif
+#ifdef CONFIG_NUMA_BALANCING
+        int numa_scan_seq;
+        int numa_migrate_seq;
+        unsigned int numa_scan_period;
+        u64 node_stamp;                 /* migration stamp  */
+        struct callback_head numa_work;
+#endif /* CONFIG_NUMA_BALANCING */
+
         struct rcu_head rcu;
 
         /*
@@ -1541,6 +1597,7 @@ struct task_struct {
                 unsigned long nr_pages; /* uncharged usage */
                 unsigned long memsw_nr_pages; /* uncharged mem+swap usage */
         } memcg_batch;
+        unsigned int memcg_kmem_skip_account;
 #endif
 #ifdef CONFIG_HAVE_HW_BREAKPOINT
         atomic_t ptrace_bp_refcnt;
@@ -1553,6 +1610,18 @@ struct task_struct {
 /* Future-safe accessor for struct task_struct's cpus_allowed. */
 #define tsk_cpus_allowed(tsk) (&(tsk)->cpus_allowed)
 
+#ifdef CONFIG_NUMA_BALANCING
+extern void task_numa_fault(int node, int pages, bool migrated);
+extern void set_numabalancing_state(bool enabled);
+#else
+static inline void task_numa_fault(int node, int pages, bool migrated)
+{
+}
+static inline void set_numabalancing_state(bool enabled)
+{
+}
+#endif
+
 /*
  * Priority of a process goes from 0..MAX_PRIO-1, valid RT
  * priority is 0..MAX_RT_PRIO-1, and SCHED_NORMAL/SCHED_BATCH
@@ -1710,12 +1779,6 @@ static inline int is_global_init(struct task_struct *tsk)
         return tsk->pid == 1;
 }
 
-/*
- * is_container_init:
- * check whether in the task is init in its own pid namespace.
- */
-extern int is_container_init(struct task_struct *tsk);
-
 extern struct pid *cad_pid;
 
 extern void free_task(struct task_struct *tsk);
@@ -1729,8 +1792,8 @@ static inline void put_task_struct(struct task_struct *t)
                 __put_task_struct(t);
 }
 
-extern void task_times(struct task_struct *p, cputime_t *ut, cputime_t *st);
-extern void thread_group_times(struct task_struct *p, cputime_t *ut, cputime_t *st);
+extern void task_cputime_adjusted(struct task_struct *p, cputime_t *ut, cputime_t *st);
+extern void thread_group_cputime_adjusted(struct task_struct *p, cputime_t *ut, cputime_t *st);
 
 /*
  * Per process flags
@@ -1844,14 +1907,6 @@ static inline void rcu_copy_process(struct task_struct *p)
 
 #endif
 
-static inline void rcu_switch(struct task_struct *prev,
-                              struct task_struct *next)
-{
-#ifdef CONFIG_RCU_USER_QS
-        rcu_user_hooks_switch(prev, next);
-#endif
-}
-
 static inline void tsk_restore_flags(struct task_struct *task,
                                 unsigned long orig_flags, unsigned long flags)
 {
@@ -1990,6 +2045,13 @@ enum sched_tunable_scaling {
 };
 extern enum sched_tunable_scaling sysctl_sched_tunable_scaling;
 
+extern unsigned int sysctl_numa_balancing_scan_delay;
+extern unsigned int sysctl_numa_balancing_scan_period_min;
+extern unsigned int sysctl_numa_balancing_scan_period_max;
+extern unsigned int sysctl_numa_balancing_scan_period_reset;
+extern unsigned int sysctl_numa_balancing_scan_size;
+extern unsigned int sysctl_numa_balancing_settle_count;
+
 #ifdef CONFIG_SCHED_DEBUG
 extern unsigned int sysctl_sched_migration_cost;
 extern unsigned int sysctl_sched_nr_migrate;
@@ -2271,7 +2333,7 @@ extern void mm_release(struct task_struct *, struct mm_struct *);
 extern struct mm_struct *dup_mm(struct task_struct *tsk);
 
 extern int copy_thread(unsigned long, unsigned long, unsigned long,
-                        struct task_struct *, struct pt_regs *);
+                        struct task_struct *);
 extern void flush_thread(void);
 extern void exit_thread(void);
 
@@ -2283,14 +2345,13 @@ extern void flush_itimer_signals(void);
 
 extern void do_group_exit(int);
 
-extern void daemonize(const char *, ...);
 extern int allow_signal(int);
 extern int disallow_signal(int);
 
 extern int do_execve(const char *,
                      const char __user * const __user *,
-                     const char __user * const __user *, struct pt_regs *);
-extern long do_fork(unsigned long, unsigned long, struct pt_regs *, unsigned long, int __user *, int __user *);
+                     const char __user * const __user *);
+extern long do_fork(unsigned long, unsigned long, unsigned long, int __user *, int __user *);
 struct task_struct *fork_idle(int);
 #ifdef CONFIG_GENERIC_KERNEL_THREAD
 extern pid_t kernel_thread(int (*fn)(void *), void *arg, unsigned long flags);